arXiv Machine Learning By Huanshu Zhang, Lei Kang, Yuyan Chen, Luxiang Wang, Zhaolong Cao, Douglas H. Werner

Towards a universal meta-optics solver via large language models

Read the original on arXiv Machine Learning →

The paper introduces a unified large language model workflow for modeling and inverse-design of metasurfaces across multiple families. By converting geometries, design parameters, and optical responses into a shared instruction‑following text format, the authors fine‑tune Gemma‑2‑9B on eight distinct metasurface families. Compared to single‑family models, the joint model predicts all families’ optical responses simultaneously and reduces mean‑squared error by an average of 56.5%. "whyItMatters":"The approach demonstrates that a shared sequence‑based LLM interface can streamline cross‑family metasurface design, eliminating the need for separate surrogate architectures for each geometry class."

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Aug 20

A Comprehensive Review of Large Language Models for Nanophotonics: From Surrogate Modeling to Autonomous Design

The review examines how Large Language Models (LLMs) enhance nanophotonics design by providing semantic interfaces, code generation, and tool orchestration. It traces the evolution from classical neural networks to transformer-based models and categorizes LLM applications into surrogate models that map structure to spectrum and agentic systems that generate code and orchestrate simulations for closed-loop optimization. The article also highlights potential cross-disciplinary uses of LLMs in materials science and wireless communications, and envisions future multimodal foundation models that actively collaborate in autonomous scientific discovery.

By Huanshu Zhang, Kegeng Tang, Lei Kang, Sawyer D. Campbell, Zihao Wang, Douglas H. Werner
arXiv AI
Aug 25

MOCLIP: A Foundation Model for Large-Scale Nanophotonic Inverse Design

MOCLIP (Metasurface Optics Contrastive Learning Pretrained) is a nanophotonic foundation model that unifies metasurface geometry and spectra in a shared latent space using contrastive learning on an ImageNet‑1K–sized experimental dataset. It enables high‑throughput zero‑shot inverse design, predicting 0.2 million samples per second and allowing the design of a full 4‑inch wafer of high‑density metasurfaces in minutes. The model also supports generative latent‑space optimization with 97 % accuracy and demonstrates an optical information storage concept achieving 0.1 Gbit/mm², six times higher than commercial optical media.

By S. Rodionov, A. Burguete-Lopez, M. Makarenko, Q. Wang, F. Getman, A. Fratalocchi
arXiv Computer Vision
Sep 7

Collaborative On-Sensor Array Cameras

The paper presents a collaborative on‑sensor array camera that uses a distributed meta‑optics learning method to jointly optimize a 100‑million‑nanopost metasurface array for broadband visible imaging. By training the array end‑to‑end with a learned meta‑atom proxy and a parallax‑aware, noise‑aware reconstruction algorithm, the design overcomes the wavelength‑dependent limitations of traditional metalenses. Experimental results show that the camera delivers consistent image quality across varying scene illumination spectra without relying on generative reconstruction.

By Jipeng Sun, Kaixuan Wei, Thomas Eboli, Congli Wang, Cheng Zheng, Zhihao Zhou, Arka Majumdar, Wolfgang Heidrich, Felix Heide
arXiv AI
Jul 13

A Self-Evolving Agentic Framework for Metasurface Inverse Design

arXiv:2604. 01480v2 Announce Type: replace Abstract: Metasurface inverse design can realize complex optical functionality, but turning a target optical response into executable optimization code still requires substantial expertise in computational electromagnetics and solver-specific software engineering.

By Yi Huang, Bowen Zheng, Yunxi Dong, Hong Tang, Huan Zhao, S. M. Rakibul Hasan Shawon, Hualiang Zhang
arXiv AI
Aug 19

Inductively Scalable, Single-Step Neural Surrogates for Wave-Scattering Inverse Problems

The paper presents a method for training single‑step neural surrogates that can handle wave‑scattering problems with tens of thousands of controllable variables. By dynamically generating training examples that highlight surrogate errors and using a replay dataset with normalization, the authors achieve a surrogate that accurately simulates two‑dimensional wave scattering for up to 41,772 variables and generalizes to over 3 million variables without retraining. The surrogate is applied to forward simulations and inverse design of freeform beam splitters and gradient‑index lenses, achieving speedups up to 26.5× compared to traditional FDTD methods.

By Charles Dove, Laura Waller